Baruffaldi's blog

From scikit-learn to Faiss: Migrating PCA for Scalable Vector Search

Keep sklearn for training and validation, while leveraging Faiss for high-performance production inference.

Jul 19, 2025 •

Share "From scikit-learn to Faiss: Migrating PCA for Scalable Vector Search"

Share on: Facebook • Twitter

How to Start a Machine Learning Project Before Starting a Machine Learning Project

Ever started a machine learning project, only to realize you were solving the wrong problem? Essential tips to steer your ML projects toward real impact!

Jul 9, 2024 •

Share "How to Start a Machine Learning Project Before Starting a Machine Learning Project"

Share on: Facebook • Twitter

DVC + Many Files: A Strategy for Efficient Large Dataset Management

Unaware that DVC struggles with large datasets? It was also a surprise for us.

Jun 30, 2024 •

Share "DVC + Many Files: A Strategy for Efficient Large Dataset Management"

Share on: Facebook • Twitter